[
https://issues.apache.org/jira/browse/SPARK-5224?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Josh Rosen updated SPARK-5224:
------------------------------
Assignee: Davies Liu
> parallelize list/ndarray is really slow
> ---------------------------------------
>
> Key: SPARK-5224
> URL: https://issues.apache.org/jira/browse/SPARK-5224
> Project: Spark
> Issue Type: Bug
> Components: PySpark
> Affects Versions: 1.2.0
> Reporter: Davies Liu
> Assignee: Davies Liu
> Priority: Blocker
> Fix For: 1.3.0, 1.2.1
>
>
> After the default batchSize changed to 0 (batched based on the size of
> object), but parallelize() still use BatchedSerializer with batchSize=1.
> Also, BatchedSerializer did not work well with list and numpy.ndarray
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
